conftrace_

reward estimation

31 papers

Explore in graph

Co-occurring keywords

reinforcement learning (4352) contextual bandit (381) multi-armed bandit (1098) variance reduction (523) policy learning (702) online learning (1777) dialogue policy (60) regret bound (1926) bandit feedback (118) inverse reinforcement learning (205)

Papers

Efficient Counterfactual Learning from Bandit Feedback AAAI 2019
A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning IJCAI 2018
Reward Estimation for Variance Reduction in Deep Reinforcement Learning CORL 2018
Profile-Based Bandit with Unknown Profiles JMLR 2018
On-line Dialogue Policy Learning with Companion Teaching EACL 2017
Towards a learning-theoretic analysis of spike-timing dependent plasticity NIPS 2012